Inteligência Artificial
Code
100101
Academic unit
NOVA Information Management School
Credits
6.0
Teacher in charge
Sara Guilherme Oliveira da Silva
Teaching language
Portuguese. If there are Erasmus students, classes will be taught in English
Objectives
To provide the students with the historical and current context of Artificial Intelligence. To teach the functioning of a wide array of Artificial Intelligence methods, from the most classical techniques of search and reasoning to the most cutting-edge methods of machine learning. To raise awareness to the issue of ethics in Artificial Intelligence.
Prerequisites
None. This is an introductory course, with a wide range of contents, but not very deep, in particular on the most advanced methods. No programming skills required. The mathematics used is extremely basic.
Subject matter
Introduction
- Presentation of the course
- History and fiction of AI
- Definition and main concepts
Knowledge Representation and Reasoning
- Goal trees
- Facts and rules
- Inference
- Prolog
- Uncertainty: Fuzzy and Probabilistic Inference Systems
- Ontologies and Semantic Web
Search
- Basic search
- Heuristic search
- Optimal search
- State space and dynamic environments
- Search with constraints
- Evaluation of heuristics
Games
- Minimax algorithm
- Minimax with Alpha-Beta
- Iterative deepening
Machine Learning
- Introduction, motivation and definition
- Hierarquical clustering and K-Means
- K-Nearest Neighbors
- Decision Trees and Random Forests
- Neural Networks: Multilayer Perceptron, Deep Learning
- Support Vector Machines
- Evolutionary Computation: Genetic Algorithms and Genetic Programming
Complex Systems
Ethics in AI (transversal topic)
Bibliography
The WWWW (Wonderful World Wide Web).
Teaching method
Lessons include:
- Theoretical explanations (on the white board)
- Demos (on the computer)
- Exercises (on paper)
- Usage of some software (on the computer)
- Tutorials by invited lecturers
In the classroom, pen and paper are MANDATORY!
There will be very few PDF materials. Students MUST attend classes.
Evaluation method
Open-book mini-tests during the semester (40%). Closed-book written exam in the end of the semester (60%).